Search Results for author: Michael Blumenstein

Found 18 papers, 2 papers with code

Dual-Personalizing Adapter for Federated Foundation Models

no code implementations28 Mar 2024 Yiyuan Yang, Guodong Long, Tao Shen, Jing Jiang, Michael Blumenstein

To address challenges in this new setting, we explore a simple yet effective solution to learn a comprehensive foundation model.

Federated Learning

FAST: Font-Agnostic Scene Text Editing

no code implementations5 Aug 2023 Alloy Das, Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein

However, most of the existing STE methods show inferior editing performance because of (1) complex image backgrounds, (2) various font styles, and (3) varying word lengths within the text.

Scene Text Editing Style Transfer +1

Global Context-Aware Person Image Generation

no code implementations28 Feb 2023 Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein

The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context.

Image Generation

TIPS: Text-Induced Pose Synthesis

no code implementations24 Jul 2022 Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein

In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person.

Descriptive Pose Transfer

Scene Aware Person Image Generation through Global Contextual Conditioning

no code implementations6 Jun 2022 Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein

Finally, the target image is generated from the refined skeleton using another generative network conditioned on a given image of the target person.

Generative Adversarial Network Image Generation

A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video

no code implementations26 May 2020 Sauradip Nag, Palaiahnakote Shivakumara, Umapada Pal, Tong Lu, Michael Blumenstein

The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions.

Clustering Text Detection

Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy

no code implementations10 May 2020 Miaohua Zhang, Yongsheng Gao, Changming Sun, Michael Blumenstein

Traditional tensor decomposition methods, e. g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers.

Clustering Face Reconstruction +3

A Robust Matching Pursuit Algorithm Using Information Theoretic Learning

no code implementations10 May 2020 Miaohua Zhang, Yongsheng Gao, Changming Sun, Michael Blumenstein

Current orthogonal matching pursuit (OMP) algorithms calculate the correlation between two vectors using the inner product operation and minimize the mean square error, which are both suboptimal when there are non-Gaussian noises or outliers in the observation data.

Image Reconstruction

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

3 code implementations ICLR 2022 Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, Jing Jiang

Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multiple prime numbers according to the length of the time series.

General Classification Time Series +2

Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis

no code implementations19 Dec 2019 Chandranath Adak, Bidyut. B. Chaudhuri, Chin-Teng Lin, Michael Blumenstein

In this paper, we work on intra-variable handwriting, where the writing samples of an individual can vary significantly.

Temporal Self-Attention Network for Medical Concept Embedding

1 code implementation15 Sep 2019 Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Jing Jiang, Michael Blumenstein

In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept.


FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition

no code implementations20 Apr 2019 Qingqing Wang, Wenjing Jia, Xiangjian He, Yue Lu, Michael Blumenstein, Ye Huang

Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role.

Scene Text Recognition

Bag-of-Visual-Words for Signature-Based Multi-Script Document Retrieval

no code implementations18 Jul 2018 Ranju Mandal, Partha Pratim Roy, Umapada Pal, Michael Blumenstein

Finally, three distance measures were used to match a query signature with the signature present in target documents for retrieval.


Towards a Dedicated Computer Vision Tool set for Crowd Simulation Models

no code implementations1 Sep 2017 Sultan Daud Khan, Muhammad Saqib, Michael Blumenstein

Understanding underlying dynamics and behavior of crowd is becoming areas of interest for most of computer scientists.

Crowd Counting

Can Walking and Measuring Along Chord Bunches Better Describe Leaf Shapes?

no code implementations CVPR 2017 Bin Wang, Yongsheng Gao, Changming Sun, Michael Blumenstein, John La Salle

A novel chord bunch walks (CBW) descriptor is developed through the chord walking that effectively integrates the shape image function over the walked chord to reflect the contour features and the inner properties of the shape.


Cannot find the paper you are looking for? You can Submit a new open access paper.